{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:742LGJGJ343KNSH6YXILGOEHPD","short_pith_number":"pith:742LGJGJ","schema_version":"1.0","canonical_sha256":"ff34b324c9df36a6c8fec5d0b3388778fca2b2985ac04b55f5ac2548411a5392","source":{"kind":"arxiv","id":"2402.09910","version":2},"attestation_state":"computed","paper":{"title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andr\\'e V. Duarte, Arlindo L. Oliveira, Lei Li, Xuandong Zhao","submitted_at":"2024-02-15T12:17:15Z","abstract_excerpt":"How can we detect if copyrighted content was used in the training process of a language model, considering that the training data is typically undisclosed? We are motivated by the premise that a language model is likely to identify verbatim excerpts from its training text. We propose DE-COP, a method to determine whether a piece of copyrighted content was included in training. DE-COP's core approach is to probe an LLM with multiple-choice questions, whose options include both verbatim text and their paraphrases. We construct BookTection, a benchmark with excerpts from 165 books published prior"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.09910","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T12:17:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dcdca98379857e23baae4f9becd110f8ee72323ecbc1c3ac40dbc831ab1fc1da","abstract_canon_sha256":"7b57bf4c0b40586c3adae8672ef1f72cd79978e8e849a8056c9608e93fde1e4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:22.424071Z","signature_b64":"51HIwiZ1YE+HMV4j8SNw0xQuQnUNGPsRoDBWtty7bzkpsnRd2rnKuBhTCXvrHa8QaZwWb3bQJ9P9n/eGAMfQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff34b324c9df36a6c8fec5d0b3388778fca2b2985ac04b55f5ac2548411a5392","last_reissued_at":"2026-07-05T08:36:22.423655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:22.423655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andr\\'e V. Duarte, Arlindo L. Oliveira, Lei Li, Xuandong Zhao","submitted_at":"2024-02-15T12:17:15Z","abstract_excerpt":"How can we detect if copyrighted content was used in the training process of a language model, considering that the training data is typically undisclosed? We are motivated by the premise that a language model is likely to identify verbatim excerpts from its training text. We propose DE-COP, a method to determine whether a piece of copyrighted content was included in training. DE-COP's core approach is to probe an LLM with multiple-choice questions, whose options include both verbatim text and their paraphrases. We construct BookTection, a benchmark with excerpts from 165 books published prior"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09910","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.09910/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.09910","created_at":"2026-07-05T08:36:22.423711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09910v2","created_at":"2026-07-05T08:36:22.423711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09910","created_at":"2026-07-05T08:36:22.423711+00:00"},{"alias_kind":"pith_short_12","alias_value":"742LGJGJ343K","created_at":"2026-07-05T08:36:22.423711+00:00"},{"alias_kind":"pith_short_16","alias_value":"742LGJGJ343KNSH6","created_at":"2026-07-05T08:36:22.423711+00:00"},{"alias_kind":"pith_short_8","alias_value":"742LGJGJ","created_at":"2026-07-05T08:36:22.423711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.04244","citing_title":"Benchmark Data Contamination of Large Language Models: A Survey","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/742LGJGJ343KNSH6YXILGOEHPD","json":"https://pith.science/pith/742LGJGJ343KNSH6YXILGOEHPD.json","graph_json":"https://pith.science/api/pith-number/742LGJGJ343KNSH6YXILGOEHPD/graph.json","events_json":"https://pith.science/api/pith-number/742LGJGJ343KNSH6YXILGOEHPD/events.json","paper":"https://pith.science/paper/742LGJGJ"},"agent_actions":{"view_html":"https://pith.science/pith/742LGJGJ343KNSH6YXILGOEHPD","download_json":"https://pith.science/pith/742LGJGJ343KNSH6YXILGOEHPD.json","view_paper":"https://pith.science/paper/742LGJGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09910&json=true","fetch_graph":"https://pith.science/api/pith-number/742LGJGJ343KNSH6YXILGOEHPD/graph.json","fetch_events":"https://pith.science/api/pith-number/742LGJGJ343KNSH6YXILGOEHPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/742LGJGJ343KNSH6YXILGOEHPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/742LGJGJ343KNSH6YXILGOEHPD/action/storage_attestation","attest_author":"https://pith.science/pith/742LGJGJ343KNSH6YXILGOEHPD/action/author_attestation","sign_citation":"https://pith.science/pith/742LGJGJ343KNSH6YXILGOEHPD/action/citation_signature","submit_replication":"https://pith.science/pith/742LGJGJ343KNSH6YXILGOEHPD/action/replication_record"}},"created_at":"2026-07-05T08:36:22.423711+00:00","updated_at":"2026-07-05T08:36:22.423711+00:00"}